Article Per Year (5 Year)
p-Index From 2021 - 2026
3.461
P-Index
This Author published in this journals
All Journal Indonesian Journal of Electronics and Instrumentation Systems Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Proceedings of KNASTIK Jurnal sistem informasi, Teknologi informasi dan komputer JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Bulletin of Computer Science Research Jurnal Pengabdian kepada Masyarakat Bina Darma Algoritme Jurnal Mahasiswa Teknik Informatika Arcitech: Journal of Computer Science and Artificial Intelligence Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS MDP Student Conference
Wijang Widhiarso
Universitas Multi Data Palembang
Agriculture, Biological Sciences & Forestry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Library & Information Science Mathematics Social Sciences Other

Published : 27 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 27 Documents
Search

 1   2   3 
Klasifikasi Citra Sampah Botol Plastik Jenis HDPE dan PET Menggunakan Algoritma YOLOv7 Purwasih, Opita; Widhiarso, Wijang; Muhammad Rizky Pribadi
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.654

Abstract

The classification of plastic bottle waste, particularly High Density Polyethylene (HDPE) and Polyethylene Terephthalate (PET), remains a challenge in recycling processes due to their similar visual characteristics. Misclassification can lead to a decline in recycled material quality and economic losses in the waste management industry. This research aims to develop an automated image-based classification system to distinguish between HDPE and PET plastic waste using the You Only Look Once version 7 (YOLOv7) object detection algorithm. The dataset consists of plastic bottle images in various physical conditions, annotated with bounding boxes to support model training. The data were split into 70% for training, 20% for validation, and 10% for testing. The best performance was achieved with a batch size of 16 and 100 training epochs, resulting in a precision of 93.9%, recall of 91.6%, and a mean Average Precision (mAP@0.5) of 96.5%. The model demonstrated the ability to accurately classify both types of plastic bottles, even when objects were deformed. These results suggest that the YOLOv7 algorithm is highly capable for implementation in image-based waste classification systems, enhancing sorting efficiency and supporting more sustainable plastic waste management practices.
Klasifikasi Otomatis Tingkat Kerusakan Retak Bangunan pada Citra Digital Menggunakan MobileNetV2 dan Augmentasi Data Ricky Putra Sardika; Widhiarso, Wijang
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 5 No. 1 (2025): June 2025
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v5i1.13938

Abstract

Crack detection in buildings is a crucial step in maintaining structural integrity at an early stage and preventing further damage. This study aims to improve the accuracy of crack severity classification in digital images by applying five on-the-fly data augmentation techniques (flip, rotate, zoom, translation, and contrast) combined with the MobileNetV2 architecture. The augmentation techniques are performed dynamically during the training process without storing the transformed images, making the process more efficient in terms of storage, computation time, and adaptability to data variations. This study utilized a dataset of 900 images and achieved a classification accuracy of 93%, which is higher than the previous approach using MobileNetV1 with offline augmentation that only reached 89%. Previous research was limited to static augmentation approaches and less efficient CNN architectures. This study addresses those limitations by integrating dynamic augmentation and a lightweight architecture. It contributes to enhancing the efficiency and accuracy of crack image classification models in the context of limited data and low-computation systems, with strong potential for implementation in automated detection systems on mobile or edge computing devices.
CLASSIFICATION OF PNEUMONIA USING K-NEAREST NEIGHBOR METHOD WITH GLCM EXTRACTION Wijaya, Chandra; Irsyad, Hafiz; Widhiarso, Wijang
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 1 No 1 (2020): Oktober 2021 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1864.245 KB) | DOI: 10.35957/algoritme.v1i1.431

Abstract

Pneumonia is an inflammatory parenchymal disease caused by various microorganisms, including bacteria, micro bacteria, fungi, and viruses. This study used an X-ray to find out whether or not there was pneumonia. The objective of this study was to classify the X-ray results whether or not there was pneumonia in a fast and precise way through a program to produce good accuracy. The classification method used in this study were K-Nearest Neighbor (KNN) and Gray Level Co-Occurrence (GLCM) for the extraction method. There are several stages before being classified, namely cropping, resizing, contrast stretching, and thresholding. The results showed that the best accuracy per class was 66.20% for K = 5.
Klasterisasi Topik Skripsi Informatika dengan Metode DBSCAN Khan, Zicola Vladimir VIky; Alamsyah, Derry; Widhiarso, Wijang
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 3 No 1 (2022): Oktober 2022 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.3337

Abstract

This research analyzed 176 Palembang public universities’ students’ theses which were published in 2020. The data was analyzed by conducting text processing and extraction with TF-IDF feature by using two scenarios, the reduced feature value and the unreduced one, with SVD method. In each scenario, three metrics, cosine, euclidean, and, manhattan were used, which generated six scenarios in total. The result found that the best quality of cluster which was measured by silhouette coefficient comes from metric cosine and reducted by SVD with the silhouette coefficient value of 0.88382763, intracluster value of 0.08688583, and intercluster value of 0.74671096. Therefore, the cluster quality value of the reducted feature is the best among all metrics. In addition, the use of DBSCAN method showed a positive correlation between epsilon and intracluster with the value of 0.97669, and also showed a negative correlation between epsilon and silhouette with the value of 0.9789.
Klasifikasi Pengenalan Wajah Untuk Mengetahui Jenis Kelamin Menggunakan Metode Convolutional Neural Network SATRIAWAN, MUHAMMAD AKBAR; WIDHIARSO, WIJANG
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 4 No 1 (2023): Oktober 2023 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v4i1.6095

Abstract

The face is the component that is most easily recognized and is often the center of attention of other people in the human body. There are often difficulties in distinguishing and analyzing large numbers of facial images manually due to the large number of similarities between males and females, which slows down the process of gender identification. This research was made to fix this problem by using the CNN method. The dataset used is 2280 images consisting of train, valid and test. The research process includes data pre-processing, model initialization, model training, hyperparameter validation and adjustment, and model performance evaluation. The test results show an increase in accuracy and a decrease in loss as training iterations increase. In this study, results were obtained with an accuracy rate of 92%, which shows the effectiveness of using a Convolutional Neural Network (CNN) with the ResNet-50 architecture in processing and classifying male and female facial images.
PEMBERDAYAAN KADER POSYANDU DALAM PEMBUATAN MEDIA PROMOSI KESEHATAN DIGITAL MENGGUNAKAN APLIKASI CANVA Alfiarini, Alfiarini; Apriadi, Deni; Yanto, Robi; Wijang Widhiarso
Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS Vol. 3 No. 6 (2025): Desember
Publisher : CV. Alina

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59407/jpki2.v3i6.3393

Abstract

Pengabdian ini bertujuan untuk memberdayakan kader posyandu dalam meningkatkan kemampuan pembuatan media promosi kesehatan digital melalui pemanfaatan aplikasi Canva sebagai sarana pendukung edukasi kesehatan masyarakat. Metode pengabdian yang digunakan adalah pendekatan pengabdian kepada masyarakat (PKM) dengan tahapan perencanaan, persiapan, pelaksanaan, dan evaluasi, yang dilaksanakan melalui kegiatan pelatihan, praktik langsung, asistensi, serta evaluasi menggunakan pre-test, post-test, dan kuesioner umpan balik peserta. Hasil pengabdian menunjukkan adanya peningkatan kemampuan kader posyandu secara signifikan, di mana sebelum kegiatan hanya 25% peserta memiliki pengetahuan dasar desain digital, sedangkan setelah pelatihan sebanyak 90% peserta mampu membuat media promosi kesehatan secara mandiri menggunakan aplikasi Canva dan memanfaatkannya melalui media sosial. Simpulan dari kegiatan ini adalah bahwa pelatihan penggunaan aplikasi Canva efektif dalam meningkatkan kapasitas kader posyandu dalam promosi kesehatan digital serta mendukung transformasi metode edukasi kesehatan dari konvensional menuju digital yang lebih luas dan berkelanjutan.
Optimasi Keputusan Repeat-Order Marchandise K-Pop Menggunakan Algoritma Greedy Berdasarkan Matriks Profitabilitas dan Tren Widhiarso, Wijang
Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Vol. 4 No. 3 (2026): Februari 2026
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i3.829

Abstract

Industri ritel merchandise K-Pop di Indonesia mengalami dinamika permintaan yang sangat tinggi akibat pengaruh tren global, aktivitas promosi idola, serta perilaku fandom yang berubah dengan cepat. Kondisi ini menimbulkan tantangan serius dalam pengelolaan inventaris, khususnya pada pengambilan keputusan repeat order, karena kesalahan keputusan dapat berujung pada overstock, dead stock, atau kehilangan peluang keuntungan. Pendekatan konvensional seperti Economic Order Quantity (EOQ) cenderung bersifat statis dan kurang mampu mengakomodasi karakteristik permintaan merchandise K-Pop yang fluktuatif, berbasis tren, dan dipengaruhi faktor emosional konsumen. Penelitian ini bertujuan untuk mengoptimalkan keputusan repeat order merchandise grup Treasure dengan menerapkan algoritma Greedy berbasis matriks profitabilitas dan tren pasar. Data primer yang digunakan terdiri atas 60 item produk periode 2024–2026 dengan parameter harga jual, harga pokok, profit nominal per unit, margin persentase, serta velocity demand yang diperoleh dari platform e-commerce utama di Indonesia. Algoritma Greedy diimplementasikan melalui perhitungan Skor Prioritas (SP) yang mengintegrasikan profitabilitas unit, koefisien tren pasar, dan kecepatan permintaan, kemudian dilakukan pengurutan secara menurun untuk menentukan prioritas pengambilan keputusan lokal yang optimal. Hasil penelitian menunjukkan bahwa produk dengan kombinasi margin persentase tinggi dan keterikatan fandom yang kuat, seperti Treasure Official Lightstick dan lini karakter TRUZ Minini, menempati urutan prioritas repeat order tertinggi. Penerapan algoritma Greedy terbukti efektif dalam menghasilkan solusi yang cepat, efisien secara komputasi dengan kompleksitas O(n log n), serta mendekati solusi optimal global tanpa memerlukan perhitungan matematis yang kompleks. Dengan demikian, algoritma Greedy memberikan kontribusi praktis sebagai sistem pendukung keputusan yang adaptif bagi pelaku ritel K-Pop untuk meningkatkan akurasi pengadaan barang, memaksimalkan return on investment (ROI), dan memitigasi risiko inventaris pada lingkungan bisnis yang sangat dinamis.
Co-Authors ALFIARINI, ALFIARINI Andres, Yohanes Asyraq, Cerwyn Cendy Prakarsah Chandra Wijaya Dafid Dafid Deni Apriadi Derry Alamsyah Edi Winarko Edo Renaldo Ericco Andreas Ervina Patricia Arifin Farisi, Ahmad Hafiz Irsyad Kersen Kersen Khan, Zicola Vladimir VIky Kurniawan, Wiji Manalu, Josua Michael Michael Muhammad Irfan Muhammad Rachmadi, Muhammad Muhammad Rizky Pribadi Purwasih, Opita Ricky Putra Sardika Robi Yanto Sardika, Ricky Putra SATRIAWAN, MUHAMMAD AKBAR Sri Hartati Usman Usman Vera Nofita Verren Oktaviana Yohannes, Yohannes Yuda, Andika Dirma